© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 6091
    Prev
    Next
    INDEX
    Explanations

    events or occasions related to celebrating milestones or achievements

    oai_token-act-pair · gpt-3.5-turbo

    celebrations and anniversaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lycer
    -0.72
    rooms
    -0.69
     contradicts
    -0.66
     interrogated
    -0.64
     interrog
    -0.64
     Canaver
    -0.64
    perate
    -0.62
     agitated
    -0.61
     panicked
    -0.61
    ItemImage
    -0.61
    POSITIVE LOGITS
     anniversary
    1.60
     birthday
    1.33
    iversary
    1.26
     milestone
    1.24
     Anniversary
    1.20
     milestones
    1.09
     accomplishments
    1.04
     occasion
    1.03
     accomplishment
    1.03
     holidays
    1.02
    Activations Density 0.222%

    No Known Activations